Automated image systems to characterize aquatic organisms improve research and enable fast response to environmental risk situations. In November 2015, a dam in Mariana City-MG (Brazil) collapsed and led to the disposal of mud tailings from the mining process to the Doce River. The accident resulted in several casualties and incalculable damage to surrounding communities and the environment. The mud increased water turbidity, an essential condition to the functioning of the image analysis systems, and directly affected the characterization of the organisms, making it impossible to distinguish copepods in the mud, due to the blurred outline. To get a quick response evaluating environmental situations, this work aimed to develop and test different algorithms characterizing and classifying copepods by their size (length and area) using in situ images acquired by the Lightframe On-Sight Keyspecies Investigation device. Field tests were carried out under different turbidity levels throughout the gradient observed in the coastal zone adjacent to the Doce River. The best algorithm reduced nearly 50% of the noise in some images when compared with manual treatment and led to 96% accuracy in measurement and counting. Semi-automated devices that perform post-processing corrections are suitable for fast environmental evaluation under high turbidity scenarios.
References
[1]
Sahoo, P., Wilkins, C. and Yeager, J. (1997) Threshold Selection Using Renyi’s Entropy. Pattern Recognition, 30, 71-84. https://doi.org/10.1016/s0031-3203(96)00065-9
[2]
Kršinić, F., Bojanić, D., Precali, R. and Kraus, R. (2007) Quantitative Variability of the Copepod Assemblages in the Northern Adriatic Sea from 1993 to 1997. Estuarine, Coastal and Shelf Science, 74, 528-538. https://doi.org/10.1016/j.ecss.2007.05.036
[3]
Bi, H., Guo, Z., Benfield, M.C., Fan, C., Ford, M., Shahrestani, S., et al. (2015) A Semi-Automated Image Analysis Procedure for in situ Plankton Imaging Systems. PLOS ONE, 10, e0127121. https://doi.org/10.1371/journal.pone.0127121
[4]
Gorsky, G., Ohman, M.D., Picheral, M., Gasparini, S., Stemmann, L., Romagnan, J.-B., et al. (2010) Digital Zooplankton Image Analysis Using the Zooscan Integrated System. Journal of Plankton Research, 32, 285-303. https://doi.org/10.1093/plankt/fbp124
[5]
Blaschko, M.B., Holness, G., Mattar, M.A., Lisin, D., Utgoff, P.E., Hanson, A.R., et al. (2005) Automatic in situ Identification of Plankton. Proceedings of the 2005 Seventh IEEE Workshops on Applications of Computer Vision, Breckenridge, 5-7 January 2005, 79-86. https://doi.org/10.1109/acvmot.2005.29
[6]
Picheral, M., Grisoni, J.-M., Stemmann, L. and Gorsky, G. (1998) Underwater Video Profiler for the “in situ” Study of Suspended Particulate Matter. Proceedingsof IEEEOCEANS’98 Conference, Nice, 28 September-1 October 1998, 171-173. https://doi.org/10.1109/OCEANS.1998.725730
[7]
Cowen, R.K. and Guigand, C.M. (2008) In situ Ichthyoplankton Imaging System (ISIIS): System Design and Preliminary Results. Limnology and Oceanography: Methods, 6, 126-132. https://doi.org/10.4319/lom.2008.6.126
[8]
Bachiller, E. and Fernandes, J.A. (2011) Zooplankton Image Analysis Manual: Automated Identification by Means of Scanner and Digital Camera as Imaging Devices. Revista de Investigación Marina, 18, 16-37.
[9]
Lawson, G.L., Wiebe, P.H., Ashjian, C.J., Gallager, S.M., Davis, C.S. and Warren, J.D. (2004) Acoustically-Inferred Zooplankton Distribution in Relation to Hydrography West of the Antarctic Peninsula. Deep Sea Research Part II: Topical Studies in Oceanography, 51, 2041-2072. https://doi.org/10.1016/j.dsr2.2004.07.022
[10]
Ollevier, A., Mortelmans, J., Vandegehuchte, M.B., Develter, R., De Troch, M. and Deneudt, K. (2022) A Video Plankton Recorder User Guide: Lessons Learned from in situ Plankton Imaging in Shallow and Turbid Coastal Waters in the Belgian Part of the North Sea. Journal of Sea Research, 188, Article 102257. https://doi.org/10.1016/j.seares.2022.102257
[11]
Fernandez, M.A., Lopes, R.M. and Hirata, N.S.T. (2015) Image Segmentation Assessment from the Perspective of a Higher Level Task. Proceedings of the 2015 28th SIBGRAPI Conference on Graphics, Patterns and Images, Salvador, 26-29 August 2015, 111-118. https://doi.org/10.1109/sibgrapi.2015.46
[12]
Uttieri, M., Carotenuto, Y., Di Capua, I. and Roncalli, V. (2023) Ecology of Marine Zooplankton. Journal of Marine Science and Engineering, 11, Article 1875. https://doi.org/10.3390/jmse11101875
[13]
Corgnati, L., Marini, S., Mazzei, L., Ottaviani, E., Aliani, S., Conversi, A., et al. (2016) Looking Inside the Ocean: Toward an Autonomous Imaging System for Monitoring Gelatinous Zooplankton. Sensors, 16, Article 2124. https://doi.org/10.3390/s16122124
[14]
Schmid, M.S., Aubry, C., Grigor, J. and Fortier, L. (2016) The LOKI Underwater Imaging System and an Automatic Identification Model for the Detection of Zooplankton Taxa in the Arctic Ocean. Methods in Oceanography, 15, 129-160. https://doi.org/10.1016/j.mio.2016.03.003
[15]
Surový, P., Dinis, C., Marušák, R. and Ribeiro, N.D.A. (2014) Importance of Automatic Threshold for Image Segmentation for Accurate Measurement of Fine Roots of Woody Plants. Forestry Journal, 60, 244-249. https://doi.org/10.1515/forj-2015-0007
[16]
Huang, L.-K. and Wang, M.-J.J. (1995) Image Thresholding by Minimizing the Measures of Fuzziness. Pattern Recognition, 28, 41-51. https://doi.org/10.1016/0031-3203(94)e0043-k
[17]
Xu, X., Xu, S., Jin, L. and Song, E. (2011) Characteristic Analysis of Otsu Threshold and Its Applications. Pattern Recognition Letters, 32, 956-961. https://doi.org/10.1016/j.patrec.2011.01.021
[18]
Lei, B. and Fan, J. (2019) Image Thresholding Segmentation Method Based on Minimum Square Rough Entropy. Applied Soft Computing, 84, Article 105687. https://doi.org/10.1016/j.asoc.2019.105687
